The 01 Project: The Linux of The AI Industry

3.7k
01 project

In the ever-evolving landscape of technology, open-source projects have been the bedrock of innovation and community-driven development. Among these, the Linux operating system is a testament to collaborative effort’s power. Now, a new player has entered the arena, aiming to become the Linux of the artificial intelligence industry: The 01 Project.

Introduction to The 01 Project

The 01 Project is an ambitious open-source ecosystem designed for artificially intelligent devices. It combines code-interpreting language models, known as “interpreters,” with advanced speech recognition and voice synthesis capabilities. This fusion creates a powerful platform capable of powering conversational, computer-operating AI devices akin to the Rabbit R1 or the Humane Pin.

Project Website

The 01 Project Vision

The vision of the 01 Project is clear and compelling: to establish itself as the “Linux” of the AI space. This means being open, modular, and free for both personal and commercial use. The project aims to democratize AI technology, making it accessible to developers, hobbyists, and companies alike.

01OS: The Flagship Operating System

At the heart of the 01 Project is the 01OS, the flagship operating system that breathes life into AI devices. The 01OS is designed to be conversational, allowing users to interact with their devices naturally and intuitively. It’s not just about understanding commands; it’s about engaging in meaningful dialogue.

Getting Started with 01

The process is straightforward for those eager to dive into the 01 Project. The project’s GitHub repository provides all the necessary instructions for setting up the server, services, and client. Installation is a breeze, with clear commands for dependency installation and running the 01 CLI. Here, we will guide you on how to set it up and make use of it.

Captive portal

To connect your 01, you will use the captive portal.

  1. Turn on your computer or laptop and connect to the ‘01 light’ Wi-Fi network.
  2. Enter your Wi-Fi/hotspot name and password in the captive portal page.
  3. Enter the server URL generated on their computer and hit ‘Connect’.

Now you’re connected and ready to go!

​Local 01OS

​Prerequisites

There are a few packages that need to be installed to run 01OS on your computer

# MacOS
brew install portaudio ffmpeg cmake

# Ubuntu
sudo apt-get install portaudio19-dev ffmpeg cmake

​Install 01 Project

To install the 01 CLI

# Clone the repo and navigate into the 01OS directory
git clone https://github.com/OpenInterpreter/01.git

​Run the 01 Project

To run 01 on your computer, use Poetry

Navigate to the project’s 01OS directory:

cd 01OS

Install your project along with its dependencies in a virtual environment managed by Poetry.

poetry install

Run your local version of 01 with:

poetry run 01

​Swap out service providers

You can set your LLM, STT, and TTS service providers

​Server setup

Run Server

poetry run 01  --server

​Configure

A core part of the 01 server is the interpreter which is an instance of Open Interpreter. Open Interpreter is highly configurable and only requires updating a single file.

# Edit i.py
01OS/01OS/server/i.py

Properties such as model, context_window, and many more can be updated here.

​LLM service provider

If you wish to use a local model, you can use the --llm-service flag:

# use llamafile
poetry run 01 --server --llm-service llamafile

For more information about LLM service providers, check out the page on Language Models.

​Voice Interface

Both speech-to-text and text-to-speech can be configured in 01OS.

You can pass CLI flags --tts-service and/or --stt-service with the desired service provider to swap out different services

These different service providers can be found in /services/stt and /services/tts

For more information, please read about speech-to-text and text-to-speech

CLI Flags

  • --server
    Run server.
  • --server-host TEXT
    Specify the server host where the server will deploy.
    Default: 0.0.0.0.
  • --server-port INTEGER
    Specify the server port where the server will deploy.
    Default: 10001.
  • --tunnel-service TEXT
    Specify the tunnel service.
    Default: ngrok.
  • --expose
    Expose server to internet.
  • --server-url TEXT
    Specify the server URL that the client should expect.
    Defaults to server-host and server-port.
    Default: None.
  • --llm-service TEXT
    Specify the LLM service.
    Default: litellm.
  • --model TEXT
    Specify the model.
    Default: gpt-4.
  • --llm-supports-vision
    Specify if the LLM service supports vision.
  • --llm-supports-functions
    Specify if the LLM service supports functions.
  • --context-window INTEGER
    Specify the context window size.
    Default: 2048.
  • --max-tokens INTEGER
    Specify the maximum number of tokens.
    Default: 4096.
  • --temperature FLOAT
    Specify the temperature for generation.
    Default: 0.8.
  • --tts-service TEXT
    Specify the TTS service.
    Default: openai.
  • --stt-service TEXT
    Specify the STT service.
    Default: openai.
  • --local
    Use recommended local services for LLM, STT, and TTS.
  • --install-completion [bash|zsh|fish|powershell|pwsh]
    Install completion for the specified shell.
    Default: None.
  • --show-completion [bash|zsh|fish|powershell|pwsh]
    Show completion for the specified shell, to copy it or customize the installation.
    Default: None.
  • --help
    Show this message and exit.

Client Setup

Get your 01 client up and running

(lets you pick from a grid of available clients)

​ESP32 Playback

To set up audio recording + playback on the ESP32 (M5 Atom), do the following:

  1. Open Arduino IDE, and open the client/client.ino file
  2. Go to Tools -> Board -> Boards Manager, search “esp32”, then install the boards by Arduino and Espressif
  3. Go to Tools -> Manage Libraries, then install the following:
  1. The board needs to connect to WiFi. Once you flash, connect to ESP32 wifi “captive” which will get wifi details. Once it connects, it will ask you to enter 01OS server address in the format “domain.com:port” or “ip:port”. Once its able to connect you can use the device.
  2. To flash the .ino to the board, connect the board to the USB port, select the port from the dropdown on the IDE, then select the M5Atom board (or M5Stack-ATOM if you have that). Click on upload to flash the board.

​Desktop

​Server with a client

# run 01 with no args
poetry run 01

​Client only

poetry run 01 --client

Flags

  • --client
    Run client.
  • --client-type TEXT
    Specify the client type.
    Default: auto.

The Community and Support

The 01 Project thrives on community involvement. With support channels like Discord and GitHub, users and developers can connect, share insights, and contribute to the project’s growth. The project’s open-source nature invites collaboration and ensures that the platform remains at the cutting edge of AI technology.

The Future of 01 Project

As the 01 Project continues to develop, its potential impact on the AI industry is immense. By providing a robust, open-source platform for AI development, the 01 Project paves the way for a future where AI is more accessible, versatile, and integrated into our daily lives.

Conclusion

The 01 Project stands as a beacon of open-source innovation in the AI industry. With its commitment to openness, modularity, and accessibility, it is poised to become the Linux of AI, shaping the future of how we interact with technology.

Exit mobile version